© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4054
    Prev
    Next
    INDEX
    Explanations

    words related to quantity or ending up in a situation

    oai_token-act-pair · gemini-2.0-flash

    the ending -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.02
    WebElementEntity
    -0.83
    UnsafeEnabled
    -0.81
    titleMargin
    -0.80
    windowFixed
    -0.80
     NSCoder
    -0.79
    webElementXpaths
    -0.79
    tanleria
    -0.78
     SwitchCompat
    -0.73
    addCriterion
    -0.73
    POSITIVE LOGITS
     carrying
    1.07
     producing
    1.04
     running
    1.00
     organizing
    0.99
     reporting
    0.95
     acting
    0.94
     generating
    0.94
     hosting
    0.93
     receiving
    0.93
     serving
    0.93
    Activations Density 10.334%

    No Known Activations